© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110911
    Prev
    Next
    INDEX
    Explanations

    equality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    digits
    -0.08
    dto
    -0.08
    nullable
    -0.08
    -u
    -0.08
     linux
    -0.08
    zg
    -0.08
    сил
    -0.08
     Dish
    -0.08
    Fuel
    -0.08
    uels
    -0.07
    POSITIVE LOGITS
    统一
    0.11
     đều
    0.09
     uniform
    0.09
    均
    0.09
     Uniform
    0.09
    豊
    0.08
    統
    0.08
     iguais
    0.08
     kaikk
    0.08
     uniformly
    0.08
    Activations Density 0.026%

    No Known Activations